Linux两个函数mbstowcs() 与wcstombs()

展开全文

Linux两个函数mbstowcs() 与wcstombs()

Linux下面的没有命名为 WideCharToMultiByte() 和 MultiByteToWideChar() 函数，WideCharToMultiByte，MultiByteToWideChar是windows下的函数，在linux下也有类似的两个函数：

mbstowcs()
wcstombs()

值得注意的是:

size_t mbstowcs(wchar_t *wcstr,const char *mbstr,size_t count);

这个函数的第三个参数count，大小一定要是mbstr长度的2倍，否则出来的中文也会是乱码。

测试一下：

setlocale(LC_ALL,"zh_CN.GB18030");
wchar_t wcstr[20] = L"字符测试123abc";

    int len = wcslen(wcstr)+1;
    printf("len = %d \n",len);
    for(int i = 0; i < len; i++)
        printf("0x%08x ",wcstr[i]);
    printf("\n");

    char str[55] = {0};
    int n = wcstombs(str,wcstr,55);
    if(-1 == n)
    {
    perror("wcstombs ");
    exit(-1);
    }
    printf("n = %d\n",n);
    for(int i = 0; i < n+1; i++)
        printf("0x%08x ",str[i]);
    printf("\n");
    wchar_t wch[50]={0};
    int m = mbstowcs(wch,str,n);
    if(m == -1)
    {
    perror("Converting");
    exit(-1);
    }
    printf("m = %d\n",m);
    for(int i =0; i<m+1;i++)
    printf("0x%08x ",wch[i]);
    printf("\n");
    return 0;
}

还有呢，转码还可以使iconv函数族，包含以下三个函数：
iconv_t iconv_open(const char *tocode, const char *fromcode);

size_t iconv(iconv_t cd,char **inbuf,size_t *inbytesleft,char **outbuf,size_t *outbytesleft);

int iconv_close(iconv_t cd);

测试一下：

#include <stdio.h>
#include <iconv.h>
#include <string.h>

#define BUFLEN 256

char outbuf[BUFLEN];
char inbuf[BUFLEN] = "characters convertion";

int main()
{
     char *pin = inbuf;
     char *pout = outbuf;

     int inlen = strlen(pin);
     int outlen = BUFLEN;

int retsize;

iconv_t cd;

cd = iconv_open("UTF-8", "GBK");

     if((iconv_t)-1 == cd) {
             perror("iconv_open error");
             return -1;
     }

retsize = iconv(cd, &pin, (size_t *)&inlen, &pout, (size_t *)&outlen);

     if((size_t)-1 == retsize) {
             perror("iconv error");
             return -2;
     }

     if(outlen > 0) {
             printf("%s\n", outbuf);
     }

iconv_close(cd);

return 0;
}